Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Novel moving object destination prediction algorithm

A technology for moving objects and prediction algorithms, applied in the intersection of statistics and computer information science, can solve the problem of high computational cost, and achieve the effect of overcoming the problem of data sparseness, solving the problem of data sparseness and long-term dependence, and solving long-term dependence.

Pending Publication Date: 2020-01-31
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Ying et al. use the semantic features and spatial position of the user's historical trajectory to predict the next position of the moving object, but the calculation cost of this method is high

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Novel moving object destination prediction algorithm
  • Novel moving object destination prediction algorithm
  • Novel moving object destination prediction algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] Below in conjunction with accompanying drawing, the present invention will be further described.

[0016] The invention is based on figure 1 The flow chart of , solves the problem of data sparsity and long-term dependence, and accurately predicts the trajectory destination while preventing the loss of effective information. First, the historical trajectory data and the trajectory data to be predicted are segmented, and the improved minimum description length (IMDL) method is used for processing, which preserves the characteristics of the original trajectory to a large extent, and at the same time segmented data for each trajectory. Trajectory segmentation solves the problem of data sparseness; then, using embedded technology, feature vectors are extracted, and the trajectory sequence is converted into an embedded vector sequence as the input of the prediction model. Through a part of the data set, the EP-LSTM model is first trained. When the training reaches a certain ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a moving object destination prediction algorithm. The method comprises the steps that firstly, an improved track segmentation method with the minimum description length (IMDL)is provided, weight parameters are introduced, meanwhile, a Dijkstra algorithm is used for converting the track segmentation problem into the shortest path problem of an undirected graph, the optimalsegmentation of a track is obtained, and therefore the track is simplified; then, a deep learning prediction model EP-LSTM based on embedded processing and long-short-term memory fusion is provided, and a high-dimensional input vector is converted into an embedded vector to serve as input of the model. The method has the advantages that the problems of data sparseness and long-term dependence in moving object destination prediction are effectively solved, and an excellent prediction effect is achieved by performing a large number of experimental verifications on a real data set.

Description

technical field [0001] The invention relates to a novel destination prediction algorithm for a moving object, which is a method for preprocessing, modeling and destination prediction for the trajectory of a moving object, and belongs to the cross field of statistics and computer information science. Background technique [0002] At present, many literatures use the method of data mining to solve the problem of destination prediction of moving objects, because the travel routes of moving objects frequently arriving at the destination are relatively fixed and basically will not change much. Morzy et al. used the improved Apriori algorithm to generate association rules, and predicted the location of moving objects through frequent itemsets of moving trajectory sequences in later research. Zheng Yu et al. used the user's behavior habits to propose a method to infer the user's movement route, but this method has certain limitations. The Markov model is very suitable for the pred...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06Q10/04G06F16/9537G06F16/29G06N3/04G06N3/08
CPCG06Q10/04G06F16/9537G06F16/29G06N3/08G06N3/044G06N3/045
Inventor 皮德常李冰荣候梦如
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com